Download and go through Week2Part2 video and follow the process I have to demo your dataset. Start from Week2_Part2.R script, change it according to your selected datset from Quiz2. Then submit to this link:

1. Your modified script.

2. A screenshot report showing the outputs from your rstudio after executing all activities.

Week2_Part2.R script:

setwd(“C:/Users/ialsmadi/Desktop/University_of_Cumberlands/Lectures/Week2/RScripts”)

getwd()

# Import test data

data<-read.csv(“yearly_sales.csv”)

#A 5-number summary is a set of 5 descriptive statistics for summarizing a continuous univariate data set. 

#It consists of the data set’s: minimum, 1st quartile, median, 3rd quartile, maximum

#Find the set, L, of data below the median. The 1st quartile is the median of L.

#Find the set, U, of data above the median. The 3rd quartile is the median of U.

print(summary(data))

anscombe<-read.csv(“anscombe.csv”)

print(summary(anscombe))

sd(anscombe$X)

var(anscombe$X)

sd(anscombe$x1)

var(anscombe$x1)

sd(anscombe$x2)

var(anscombe$x2)

sd(anscombe$x3)

var(anscombe$x3)

sd(anscombe$x4)

var(anscombe$x4)

sd(anscombe$y1)

var(anscombe$y1)

sd(anscombe$y2)

var(anscombe$y2)

sd(anscombe$y3)

var(anscombe$y3)

##– now some “magic” to do the 4 regressions in a loop:

ff <- y ~ x

mods <- setNames(as.list(1:4), paste0(“lm”, 1:4))

for(i in 1:4) {

ff[2:3] <- lapply(paste0(c(“y”,”x”), i), as.name)

## or ff[[2]] <- as.name(paste0(“y”, i))

## ff[[3]] <- as.name(paste0(“x”, i))

mods[[i]] <- lmi <- lm(ff, data = anscombe)

print(anova(lmi))

}

## See how close they are (numerically!)

sapply(mods, coef)

lapply(mods, function(fm) coef(summary(fm)))

## Now, do what you should have done in the first place: PLOTS

op <- par(mfrow = c(2, 2), mar = 0.1+c(4,4,1,1), oma = c(0, 0, 2, 0))

for(i in 1:4) {

ff[2:3] <- lapply(paste0(c(“y”,”x”), i), as.name)

plot(ff, data = anscombe, col = “red”, pch = 21, bg = “orange”, cex = 1.2,

xlim = c(3, 19), ylim = c(3, 13))

abline(mods[[i]], col = “blue”)

}

mtext(“Anscombe’s 4 Regression data sets”, outer = TRUE, cex = 1.5)

par(op)

plot(sort(data$num_of_orders))

hist(sort(data$num_of_orders))

plot(density(sort(data$num_of_orders)))

plot(sort(data$gender))

hist(sort(data$sales_total))

plot(density(sort(data$sales_total)))

library(lattice)

densityplot(data$num_of_orders)

# top plot

# bottom plot as log10 is actually

# easier to read, but this plot is in natural log

densityplot(log(data$num_of_orders))

densityplot(data$sales_total)

densityplot(log(data$sales_total))

hist(data$sales_total, breaks=100, main=”Sales total”,

 xlab=”sales”, col=”gray”)

# draw a line for the media

abline(v = median(data$sales_total), col = “magenta”, lwd = 4)

# use rug() function to see the actual datapoints

rug(data$sales_total)

#Boxplots can be created for individual variables or for variables by group. 

#The format is boxplot(x, data=), where x is a formula and data= denotes the data frame providing 

#the data.

boxplot(data$sales_total,data=data, main=”Dis by Sales”, 

xlab=”Sales”, ylab=”Total”)

# Boxplot of MPG by Car Cylinders, using one of R built-in datasets 

boxplot(mpg~cyl,data=mtcars, main=”Car Milage Data”, 

xlab=”Number of Cylinders”, ylab=”Miles Per Gallon”)

#in our boxplot above, we might want to draw a horizontal line at 12 where the national standard is.

abline(h = 12)

boxplot(data$sales_total,data=data, main=”Total sales Bplot”, 

xlab=”Sales”, ylab=”Total”)

# Dot chart of a single numeric vector

dotchart(mtcars$mpg, labels = row.names(mtcars),

cex = 0.6, xlab = “mpg”)

#install.packages(“ROCR”)

#library(ROCR)

# Simple Scatterplot

attach(mtcars)

plot(wt, mpg, main=”Scatterplot Example”, 

xlab=”Car Weight “, ylab=”Miles Per Gallon “, pch=19)

#The R function abline() can be used to add vertical, horizontal or regression lines to a graph

plot(data$sales_total, data$gender)

# Add fit lines

abline(lm(data$sales_total~ data$num_of_orders), col=”red”) # regression line (y~x) 

lines(lowess(data$sales_total, data$num_of_orders), col=”blue”) # lowess line (x,y)

# Basic Scatterplot Matrix

pairs(data)

pairs(data[0:2])

# Scatterplot Matrices from the car Package

install.packages(“car”)

library(car)

install.packages(“ggplot2”)

library(ggplot2)

quit()